Associative Learning Memories -SOLAR_A Matlab code presentation.
-
Upload
valeria-bordley -
Category
Documents
-
view
227 -
download
4
Transcript of Associative Learning Memories -SOLAR_A Matlab code presentation.
![Page 1: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/1.jpg)
Associative Learning Memories -SOLAR_A
Matlab code presentation
![Page 2: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/2.jpg)
Introduction
Associating SOLAR (SOLAR_A)
SOLAR_A structures are hierarchically organized and have ability to classify patterns in a network of sparsely connected neurons.
![Page 3: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/3.jpg)
Association Training Neurons learn associations between
pattern and its code. Once the training is completed, a network is capable to make necessary associations.
Testing When the network is presented with the
pattern only, it drives the associated input signals to these code values that represent the observed pattern.
![Page 4: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/4.jpg)
Signal definition
The inner signals in the network range from 0 to 1. A signal is a determinate low or determinate high if its value is 0 or 1.
0 - 0.5 weak low 0.5 - 1 weak high 0.5 “inactive”, or “high impedance”
![Page 5: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/5.jpg)
Neurons’ definitions
If a neuron is able to observe any type of statistical correlations of its input connections, it will function as an associative neuron.
Otherwise it will be a transmitting neuron.
![Page 6: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/6.jpg)
Associative neuron
A neuron is called an associative neuron when its inputs I1 and I2 are associated
Inputs I1 and I2 are associated if and only if I2 can be implied from I1 and I1 can be implied from I2 simultaneously.
![Page 7: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/7.jpg)
associative neuron
I1 and I2 are inputs an associative neuron has received in training.
It is quite clear that I1 and I2 are most likely to be simultaneously low or high although there is some noise.
This can be verified using P(I2 | I1) and P(I1 | I2), and implying values I2 from I1 and I1 from I2.
5.0Iif1,
5.0Iif0,)I,I(
1
1215f
Low I1 is associated with low I2, and high I1 is associated with high I2.
![Page 8: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/8.jpg)
Network Structure
Hierarchical structure
In horizontal direction, the neurons on one layer can only connect to the neurons on the previous layer.
![Page 9: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/9.jpg)
Network Structure
The connection in vertical direction obeys 80% Gaussian distribution with standard deviation 2
+ 20% uniform distribution
![Page 10: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/10.jpg)
Network Structure
The network uses feedback signals to pass information backwards to the associated inputs.
![Page 11: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/11.jpg)
Testing
During testing, the missing parts of the data need to be recovered from the existing data through association.
For example, in a pattern recognition problem, the associated code inputs are unknown and therefore set to 0.5.
![Page 12: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/12.jpg)
Neuron Feedback Scheme
![Page 13: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/13.jpg)
Iris Plants Database The Iris database has:
3 classes (Iris Setosa, Iris Versicolour and Iris Virginica)
4 numeric attributes (petal length, petal width , sepal length , sepal width )
150 instances of 50 instances for each class, where each class refers to a type of iris plant.
The classification objective Identify the class ID based on the input feature
(attribute) values
![Page 14: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/14.jpg)
Coding of the database The 4 features were scaled linearly and cod
ed using a sliding bar code .
Input bits from (V-Min)+1 to (V-Min)+L will be set high and remaining bits will be low
N-L=Max-Min
N
LV-Min
![Page 15: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/15.jpg)
Coding of the database
We scaled the 4 features of Iris database between 0-30, and
Set the length of L equal to 12 The total length of each feature is 42
The feature input requires 168 bits
![Page 16: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/16.jpg)
Coding of the database
In order to increase the probability that each feature is associated with sample class code, we merged the 4 features.
![Page 17: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/17.jpg)
Coding of the database
![Page 18: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/18.jpg)
Coding of the database
There are 3 classes total
We use 3M bits to code the class ID maximizing their code Hamming distance
The white part is filled by 2M-bit 0 string, while the grey part is filled by M-bit 1 string.
![Page 19: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/19.jpg)
Iris database simulation
Rows 1-168 Features
Rows 174-203 class ID
![Page 20: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/20.jpg)
Iris database simulation
![Page 21: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/21.jpg)
Glass identification database
0 2 4 6 8 10 12
5
10
15
20
Number of associative neurons per layer
Layers
Num
ber
of a
ssoc
iativ
e ne
uron
s
![Page 22: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/22.jpg)
Simulation of mixed features and class ID
code C
lass
ID
Fe
atu
re
Fe
atu
re
Fe
atu
reC
lass
ID
Cla
ss I
D
Cla
ss I
D
Cla
ss I
DF
ea
ture
Fe
atu
re
![Page 23: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/23.jpg)
Simulation of mixed features and class ID code
Iris databaseIris database
![Page 24: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/24.jpg)
Image recovery
Examples of training patterns
Testing results and recovered images of letter B and J
![Page 25: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/25.jpg)
Coding example
Samples from Iris database 5.1,3.5,1.4,0.2,Iris-setosa(class 1) 7.0,3.2,4.7,1.4,Iris-versicolor (class
2) 6.3,3.3,6.0,2.5,Iris-virginica (class
3)
![Page 26: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/26.jpg)
Coding example Coding:5.1,3.5,1.4,0.2,Iris-setosa (class
1) Pre-preparing: 51,35,14,2,1 Scaling the features (51,35,14,2)
from 0 to 30 After scaling: 7,19,2,2,1
![Page 27: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/27.jpg)
Coding example Features 7 000000011111111111100000000000000000000000 19 000000000000000000011111111111100000000000 2 001111111111110000000000000000000000000000 2 001111111111110000000000000000000000000000 Class ID 1 1111111111…1110000000…0000000000000…000
56 bits 112 bits
12 bits7 bits
![Page 28: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/28.jpg)
Coded data Matrix- Input
Features Class ID code
Input matrix
M Training data
N Testing data
![Page 29: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/29.jpg)
Matlab user interface
main.m – main function training2.m – training function testing2.m – testing function catchassociating.m– actively associati
ve neurons generate_input– coding the database
![Page 30: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/30.jpg)
parameters
columns- depth of layers rows- length of an input pattern stdr- standard deviation in vertical stdc- standard deviation in horizontal n_tests- test numbers
![Page 31: Associative Learning Memories -SOLAR_A Matlab code presentation.](https://reader035.fdocuments.us/reader035/viewer/2022062421/56649c755503460f949298bd/html5/thumbnails/31.jpg)
training.m r_distribution(meanr,stdr,rows,column
s,width) --defines distribution in vertical directio
n
normrnd(meanr,stdc,rows,columns) --defines distribution in horizontal direc
tion